Download Data Mining to support Decision Process in Decision

"Sharpening Skills.....
Serving Nation"
International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459 (Online), Volume 4, Special Issue 1, February 2014)
International Conference on Advanced Developments in Engineering and Technology (ICADET-14), INDIA.
Data Mining to support Decision Process in Decision Support
System
Keshav Jindal1, Manoj Sharma2, Dr. B. K Sharma3
1,2
Assistant Professor, 3Principal Scientific Officer, NITRA Technical Campus, Ghaziabad
[email protected], [email protected], [email protected]
Abstract-- Recent alliance use a come to of types of
decision support systems to make feasible decision support.
In lots of gear OLAP based tools are used in the industry
area enabling quite a few views on data and all the way on
or after side to side that a deductive go forward to data
analysis. Data mining make bigger the credible for decision
support by discover pattern and relatives unseen in data
and therefore enabling an inductive stir towards to data
analysis. The use of data mining to construct possible
decision support enables novel approaches to difficulty
solving. The paper introduces our approach to adding of
decision support systems with data mining methods. We
commence a data mining based decision support system
designed for creation users enabling them to use cluster rule
models to make easy decision support by means of barely a
essential level of acquaintance of data mining.
Keywords-- data mining, decision support system,
decision support, alliance rules
I.
INTRODUCTION
Modern organization use several types of decision
support systems to make easy decision support. For the
rationale of investigation and decision support in the
business area in a lot of belongings OLAP based decision
support systems are worn [2]. Performing scrutiny from
side to side OLAP follows a deductive approach of
analyzing statistics. The disadvantage of such an move
towards is that it depends on chance or even luck of
choosing the accurate dimensions at drilling-down to get
hold of the most expensive in sequence, trends and
patterns. We possibly will say that OLAP systems make
available systematic tools enabling user-led scrutiny of
the data, where the user has to get going the right
uncertainty in order to get the suitable answer [1]. Such
an approach enables above all the answers to the
questions like: “What is overall profits for the first
neighbourhood grouped by customers?” What about the
answers to the questions like: “What are characteristics
of our best customers?” Those answer cannot be
provided by OLAP systems, but by the using data
mining. Amateur dramatics analysis through data mining
follow an inductive move towards of analyzing data.
Data mining is a development of analyzing data in
command to determine implicit, but potentially useful in
turn and uncover up to that time unknown patterns and
associations hidden in data. The use of data mining to
smooth the progress of decision support can show the
way to an improved performance of decision making and
can facilitate the tackle of new types of sweat that have
not been addressed before. The amalgamation of data
mining and decision support can appreciably improve
current approach and create new approach to problem
solving, by enable the synthesis of knowledge from
experts and knowledge extract from data [1]. The paper
introduces decision support system called DMDSS (Data
Mining Decision Support System) which is based on data
mining. DMDSS enables integration of data mining keen
on decision processes by enabling repetitive creation of
data mining models. In DMDSS, data mining models be
created by data mining experts and browbeaten by
industry users.
II.
D ATA M INING
Data mining, or knowledge unearthing, is the
computer-assisted practice of digging from beginning to
end and analyzing mammoth sets of data and then
extracting the meaning of the data. Data mining rigging
envisage behaviours and future trend, allowing
businesses to formulate down to business, knowledgedriven decisions. Data mining tools can come back with
business questions with the intention of conventionally
were besides time consuming to resolve. They comb
databases for hidden patterns, finding predictive in
sequence that experts may miss since it lies external their
potential.
Data mining derive its name from the similarities
between penetrating for steep information in a large
record and withdrawal a mountain for a stratum of
valuable ore. Both processes necessitate either sifting
from side to side an immense amount of material, or
astutely penetrating it to find where the value resides.
Lord Krishna College of Engineering (An ISO 9001:2008 Certified Institute) Ghaziabad, Uttar Pradesh, INDIA. Page 41
"Sharpening Skills.....
Serving Nation"
International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459 (Online), Volume 4, Special Issue 1, February 2014)
International Conference on Advanced Developments in Engineering and Technology (ICADET-14), INDIA.
Even though data mining is still in its infancy,
company in a wide range of industries - including put on
the market, finance, wellbeing care, industrialized
shipping, and aerospace - are already using data mining
apparatus and techniques to take advantage of
chronological data. By means of pattern gratitude
technologies and statistical and mathematical techniques
to sift through warehoused in sequence, data mining
helps analysts recognize noteworthy facts, relationships,
trends, patterns, exceptions and anomalies that might or
else go unobserved. For businesses, data mining is used
to determine patterns and relationships in the statistics in
order to help make better business decisions. Data mining
can help smudge sales trends, develop smarter marketing
campaigns, and accurately envisage customer fidelity.
Specific uses of data mining embrace:
 Market segmentation - Identify the widespread
description of patrons who buy the identical
products commencing your theatre company.
 Customer shake - envisage which clientele are
likely to leave your troupe and go to a contestant.
 Fraud recognition - Identify which dealings are
most likely to be deceitful.
 Direct advertising - Identify which prediction
should be included in a mailing list to attain the
highest rejoinder rate.
 Interactive marketing - envisage what each
individual accessing a Web site is most likely
interested in considering.
 Market basket investigation - Comprehend what
products or armed forces are commonly purchased
together; e.g., beer and diapers.
 Drift scrutiny - Reveal the dissimilarity between
typical customers this month and preceding.
III.
INTEGRATING D ATA M INING AND DECISION
SUPPORT
Companies use quite a lot of types of decision support
systems to smooth the progress of decision support. For
the purposes of investigation and decision support in the
dealing area habitually OLAP based decision support
systems are worn. OLAP systems correspond to a tool
enabling decision support on a deliberate level. They
enable drill-down concept, i.e. digging through a data
warehouse on or after several viewpoints to acquire the
information the decision architect is interested in [2].
OLAP systems support investigation processes and
decision processes, where the analysts are supposed to
look for information, trends and patterns.
They do it by performance OLAP forms substitution
dimensions and drilling-down from beginning to end
them [4]. Performing analysis from first to last OLAP
follows a deductive come near of analyzing data [10].
The disadvantage of such an come within reach of is that
it depends on twist of fate or even luck of choosing the
accurate dimensions at drilling-down to acquire the most
valuable information, trends and patterns. We could say
that OLAP systems provide analytical tools enabling
user-led analysis of the data, where the user has to start
the right query in order to get the appropriate answer [5].
Such an approach enables mostly the answers to the
questions like, “what are best characteristics of our best
customer” those answer cannot be provided by OLAP
systems, but can be provided by the use of data mining,
which follows an inductive approach of analyzing data
[10].
When discussing the relation between data mining and
OLAP it is not the question of which one of them is
better or worse. Data mining enables the answers to
different questions than OLAP, i.e. it enables the solution
of different problems and to acquire different
information. Decision processes in general, depending on
problem, need both, OLAP and data mining, to get the
appropriate level of support of decision processes [6].
Several authors discuss the use of data mining to
facilitate decision support and they all confirm the value
of it. Chen and Liu argue that the use of data mining
helps institutions make critical decisions faster and with a
greater degree of confidence. They believe that the use of
data mining lowers the uncertainty in decision process
[7]. Nemati and Barko state that the use of data mining
offers companies an indispensable decision-enhancing
process to exploit new opportunities by transforming data
into valuable knowledge and a potential competitive
advantage. Authors also introduce their survey which
indicates that the use of data mining can improve the
quality and accuracy of decisions [8]. Lee and Park state
that the knowledge gained from data sources by the use
of data mining methods can be crucial for the decision
making processes. Mladenic claims that the integration of
data mining and decision support can lead to the
improved performance of decision support systems and
can enable the tackling of new types of problems that
have not been addressed before. They also argue that the
integration of data mining and decision support can
significantly improve current approaches and create new
approaches to problem solving, by enabling the fusion of
knowledge from experts and knowledge extracted from
data.
Lord Krishna College of Engineering (An ISO 9001:2008 Certified Institute) Ghaziabad, Uttar Pradesh, INDIA. Page 42
"Sharpening Skills.....
Serving Nation"
International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459 (Online), Volume 4, Special Issue 1, February 2014)
International Conference on Advanced Developments in Engineering and Technology (ICADET-14), INDIA.
3.1. Data Mining Software Tool Approach
Data mining can be used through two different
approaches. The first approach is called data mining
software tool approach where the use of data mining is
typically initiated through ad hoc data mining projects [4,
9]. Ad hoc data mining projects are initiated by a
particular objective on a chosen area which represents a
basis for the defining of the domain. They are performed
using data mining software tools which require a
significant expertise in data mining methods, databases
and/or statistics. They usually operate separately from the
data source, requiring a significant amount of additional
time spent with data export from various sources, data
import, pre-processing, post-processing and data
transformation. The result of a project is usually a report
explaining the models acquired during the project using
various data mining methods. Data mining software tool
approach has a disadvantage in a number of various
experts needed to collaborate in a project and in
transferability of results and models [11]. The latter
indicates that results and models acquired by the project
can be used for reporting, but cannot be directly utilized
in other application systems. Data mining software tool
approach represents the first generation of data mining.
3.2. Data Mining Application System Approach
The data mining software tool approach has revealed
some disadvantages. The most important of them is the
fact that due to the complexity of data mining software
tools, they can not be directly used by business users.
Data mining models are produced for business users. For
that reason we need applications which will enable them
to view and exploit data mining models effectively to
facilitate decision support. This implies to the new
approach of the use of data mining which we call data
mining application system approach. It is an approach
which focuses on business users and other decision
makers, enabling them to view and exploit data mining
models. Models are presented in a user-understandable
manner through a user friendly and intuitive GUI using
standard and graphical presentation techniques. Decision
makers can focus on specific business problems covered
by areas of analysis with the possibility of repeated
analysis in periodic time intervals or at particular
milestones. Through the use of data mining application
system approach, data mining becomes better integrated
in industry environments and their decision process.
IV.
INTRODUCTIONS O F DMDSS
Our decision to expand DMDSS was also lying on the
fact that the customary use of data mining from
beginning to end data mining software apparatus does not
bring data mining faster to business users for the reason
that of involvedness of data mining tools. Data mining
tools are very multifaceted and demand proficiency in
data mining, i.e. considerate of data mining algorithms
and parameters for algorithms. We sought after to
develop a decision support system that would enable data
mining experts to create data mining models and enable
business users to take advantage of data mining models
from beginning to end easy-to-use GUI. DMDSS was
urbanized for a wireless network operator for the
purposes of decision support in the area of analytical
CRM (Customer Relationship Management).
4.1 A Process Model for DMDSS
One of the key issues in the design of DMDSS was to
settle on the data mining process model. The process
representation for DMDSS is based on the CRISP-DM
(Cross Industry Standard Process for Data Mining)
process model. CRISP-DM process model breaks behind
the data mining performance into the following six
phases which all include a variety of tasks: business
sympathetic, data understanding, data preparation,
modelling, evaluation and deployment. CRISP-DM
process model was modified to the needs of DMDSS as a
two stage model: the training stage and the production
stage. The division into two stages is based on the
following two demands. First, DMDSS should enable
frequent creation of data mining models based on an upto-date data set for every area of examination. Second,
business users should only use it within the exploitation
phase with only the basic level of indulgent of data
mining concepts. Area of analysis is a business domain
on which industry users perform analysis and construct
decisions.
The homework stage represents the process model for
the use of DMDSS for the purposes of preparation of the
area of scrutiny for the production use (Fig. 1). During
the grounding stage, the CRISP-DM phases are
performed in multiple iterations with the emphasize on
the first five phases starting from business considerate
and ending with appraisal. The aim of executing multiple
iterations of all CRISP-DM phases for every area of
analysis is to accomplish step-by-step improvements in
several of the phases.
Lord Krishna College of Engineering (An ISO 9001:2008 Certified Institute) Ghaziabad, Uttar Pradesh, INDIA. Page 43
"Sharpening Skills.....
Serving Nation"
International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459 (Online), Volume 4, Special Issue 1, February 2014)
International Conference on Advanced Developments in Engineering and Technology (ICADET-14), INDIA.
In the business understanding phase, unimportant
redefinitions of the objectives can be made, if necessary,
according to the results of other phases, especially the
results of the appraisal phase. In the data grounding
phase the improvement in the procedures which
implement recreation of the data set can be achieved. The
data set must be recreated mechanically every night
based on the current state of data warehouse and
transactional databases. The trouble detected in the data
preparation phase can also demand changes in the data
sympathetic phase.
In the modelling and appraisal phase, the
representation is created and evaluated for several times
to allow alteration of data mining algorithms through
finding proper values of the algorithm parameters. It is
indispensable to do enough iteration in order to monitor
the level of changes in data sets and data mining models
acquired and reach the firmness of the data grounding
point and parameter values for data mining algorithms.
Figure 1: Plan of the development form for DMDSS
The mission of the preparation stage is to confirm the
pleasing of the objectives of the area of analysis for
decision support and to assure the firmness of data
preparation.
The construction stage represent the production use of
DMDSS for the area of investigation (Fig. 1). In the
production stage the importance is on the phases of
modelling, assessment and deployment, which does not
mean that other phase are not encompassed in the
construction stage. Data preparation, for case in point, is
executed automatically based on measures residential in
the preparation stage.
Modelling and appraisal are performed by a data
mining professional, while the exploitation phase is
performed by a production user.
V.
RELATED W ORKS
Some decision support systems that use data mining
have already been developed and introduced in the
literature. We introduced a decision support system based
on data mining. The system was designed to support
tactical decisions of a basketball coach during a
basketball match through suggesting tactical solutions
based on the data of the past games.
Lord Krishna College of Engineering (An ISO 9001:2008 Certified Institute) Ghaziabad, Uttar Pradesh, INDIA. Page 44
"Sharpening Skills.....
Serving Nation"
International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459 (Online), Volume 4, Special Issue 1, February 2014)
International Conference on Advanced Developments in Engineering and Technology (ICADET-14), INDIA.
The decision support system only supports the
association rules data mining method and uses the
association rule algorithm called Apriori algorithm
combined with the Decision query algorithm. The
decision support system enables the coach to submit data
about his tactical strategies and data about the game and
the rival team. After that the system provides the coach
with opinion about the chosen strategies and with
suggestions. The system is not designed to support other
domains; it only supports the basketball domain. Bose
and Sugumaran introduced the Intelligent Data Miner
(IDM) decision support system [2]. IDM is a Web-based
application system intended to provide organization-wide
decision support capability for business users. Besides
data mining it also supports some other function
categories to enable decision support: data inquiry and
multidimensional analysis through enabling OLAP views
on multidimensional data. In the data mining part of IDM
it supports the creation of models, manipulation of
models and presentation of models in various
presentation techniques of, among others, the following
data mining methods: association rules, clustering and
classifiers (classification). The system also performs data
cleansing and data preparation and provides necessary
parameters for data mining algorithms. An interesting
characteristic of IDM is that it makes a connection to an
external data mining software tool which performs data
mining model creation. The system enables predefined
and ad-hoc data mining model creation. The authors state
that the disadvantage of IDM is the fact that nontechnical
users (business users) need to have a fair amount of
understanding of data mining and that the use of data
mining and the creation of data mining models still needs
to be clearly directed by the user, especially with ad-hoc
model creation.
Lee and Park presented the Customized Sampling
Decision Support System (CSDSS) which uses data
mining [12]. CSDSS is a web-based system that enables
the user to select a process sampling method that is most
suitable according to his needs at purchasing
semiconductor products. The system enables the
autonomous generation of the available customized
sampling methods and provides the performance
information for those methods. CSDSS uses clustering
data mining method within the generation of sampling
methods. The system is not designed to hold up other
domain; it only ropes the domain mention.
VI.
CONCLUSIONS
DMDSS has now been in making for several years.
During the first year of its creation there will be supervise
and consultancy provide by the expansion squad. The
main goal of supervise and consultancy is to lend a hand
the data mining commissioner in the concern. The person
in charge for that role has an adequate amount of
knowledge, because he was a constituent of progress
team and all the time in attendance at grounding stage for
every area of scrutiny. But, he has not an adequate
amount of familiarity yet. Supervise will for the most part
cover prop up at model appraisal and model explanation
for data mining commissioner and selling users. Business
users use DMDSS at their every day work. They use
patterns and rules recognized in models as the original
acquaintance, which they use for investigation and
decision process at their work. It is fetching evident that
they are accomplishment worn to DMDSS. According to
their writing they have previously become attentive of the
advantages of incessant use of data mining for
investigation purposes. Based on the models acquired
they have previously geared up some changes in
promotion come near and they are planning a
extraordinary customer group focused operation utilizing
the acquaintance acquire in data mining models. The on
the whole important attainment after several months of
tradition is the fact that business users have really started
to recognize the potentials of data mining. All of a swift
they have got new ideas for new areas of analysis,
because they have started to realize how to define area of
investigation to acquire valuable grades.
REFERENCES
[1]
[2]
[3]
[4]
[5]
D. Mladenic, N. Lavrac, M. Bohanec, S. Moyle, Data Mining and
Decision Support: Integration and Collaboratio, Dordrecht,
Kluwer Academic Publishers, 2002
R. Bose, V. Sugumaran, Application of Intelligent Agent
Technology for Managerial Data Analysis and Mining, The
DATABASE for Advances in Information Systems, 30, 1, pp. 7794.
K.C. Chen, Decision Support System for Tourism Development:
System Dynamic Approach, Journal of Computer Information
Systems, 45, 1, pp. 104-112, 2004.
M. Goebel and L. Gruenwald. A Survey of Data Mining
Knowledge Discovery Software Tools. SIGKDD Explorations,
Vol. 1, No. 1, 1999, pp. 20-33.
D. Mladenic, N. Lavrac, M. Bohanec, S. Moyle, Data Mining and
Decision Support: Integration and Collaboratio, (Chapter 1: Data
Mining: Authors; N. Lavrac and M. Grobelnik), Kluwer
Academic Publishers, Dordrecht, 2003, The Nederlands.
Lord Krishna College of Engineering (An ISO 9001:2008 Certified Institute) Ghaziabad, Uttar Pradesh, INDIA. Page 45
"Sharpening Skills.....
Serving Nation"
International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459 (Online), Volume 4, Special Issue 1, February 2014)
International Conference on Advanced Developments in Engineering and Technology (ICADET-14), INDIA.
[6]
G.A. Forgionne and B. Rudenstein Montano, B. Post Data Mining
Analysis for Decision Support Through Econometrics.
Information, Knowledge, Systems Management, Vol. 1, No. 2,
1999, pp. 145-157.
[7] S.Y. Chen and X. Liu. The Contribution of Data Mining to
Information Science. Journal of Information Science, Vol. 30, No.
6, 2004, pp. 550-558.
[8] H. Nemati and C.D. Barko. Enhancing Enterprise Decisions
Through Organizational Data Mining. Journal of Computer
Information Systems, Vol. 42, No. 4, 2002, pp. 21- 28.
[9] M. Holsheimer, M. Data Mining by Business Users: Integrating
Data Mining in Business Process. Proceedings of International
Conference on Knowledge Discovery and Data Mining KDD-99,
1999, pp. 266-291.
[10] JSR-73 Expert Group. JavaTM pecification Request 73: JavaTM
Data Mining (JDM), 2004, Java Community Process.
[11] J. Srivastava, R. Cooley, M. Deshpande and P.N. Tan. Web Usage
Mining: Discovery and Applications of Usage Patterns from Web
Data. SIGKDD Explorations, Vol. 1, No. 2, 2000, pp. 12-23.
[12] H.L. Lee, C. Park, Agent and Data Mining Based Decision
Support System and its Adaption to a New Customer Centric
Electronic Commerce, Expert Systems With Applications, 25, 4,
pp. 619-635, 2003.
AUTHOR’S PROFILE
Keshav Jindal received the B.E. degree in Computer Sc. &
Engg with Honours from Vaish College of Engineering,
Rohtak. He obtained his M.Tech degree in Computer
Engineering from P.D.M.C.E. He is working as Assistant
Professor in Deptt of Computer Sc. & Engg, NITRA Technical
Campus (Govt. Aided Self Finance), Ghaziabad. He has
published more than 20 papers in national and international
journals and conferences.
Manoj Sharma received the B.E. degree in Computer Sc. &
Engg with Honours from Vaish College of Engineering,
Rohtak. He obtained his M.Tech degree in Software
Engineering from U.I.E.T, M.D.U Rohtak. He is working as
Assistant Professor in Deptt of Computer Sc. & Engg, NITRA
Technical Campus (Govt. Aided Self Finance), Ghaziabad. He
has published more than 06 papers in national and international
journals and conferences.
Dr. B.K. Sharma is M.Tech. & Ph.D. (Computer Science)
from University of Rajasthan and also certified internal auditor
course ISO-9000 from world-wide quality management
network Ltd., London (UK). He has over 23 years of experience
in academic, Industry and research. Currently Dr. Sharma is
Principal Scientific Officer & Head Software Development
Centre, NITRA, Ghaziabad. Northern India Textile Research
Association (NITRA) one of the four textile research
association and linked to the Ministry of Textile, Govt. of India.
Lord Krishna College of Engineering (An ISO 9001:2008 Certified Institute) Ghaziabad, Uttar Pradesh, INDIA. Page 46